© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 273
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "anyone" or a lack of accountability towards individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.29
    1.4%
    25
    +0.10
    0.5%
    1296
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    25
    +0.29
    0.05
    1691
    +0.10
    0.05
    1103
    +0.10
    0.04
    Negative Logits
    <bos>
    -2.94
    /***
    
    -0.83
    ⓧ
    -0.82
    <?
    -0.78
    
    
    -0.75
    /*
    -0.74
    #![
    -0.64
    <?
    
    -0.62
    //---
    -0.61
    /**
    -0.61
    POSITIVE LOGITS
     churrasco
    1.06
     riviera
    1.04
     lele
    1.01
     bandung
    1.00
     chrysler
    0.99
     ibiza
    0.99
     riva
    0.96
     maroc
    0.94
     Minang
    0.94
     megane
    0.92
    Activations Density 0.110%

    No Known Activations